jh-parking/toolrl-sft-5e-4-step750
Updated
Jonghyun Park
jh-parking
AI & ML interests
None yet
Recent Activity
published a model 9 days ago
jh-parking/toolrl-grpo-5e-6-step300 published a model 9 days ago
jh-parking/toolrl-grpo-1e-5-step300 published a model 9 days ago
jh-parking/toolrl-grpo-3e-5-step300Organizations
None yet
models 36
jh-parking/toolrl-sft-3e-4-step750
Updated
jh-parking/toolrl-sft-5e-5-step750
Updated
jh-parking/toolrl-grpo-5e-5-step300
Updated
jh-parking/toolrl-grpo-3e-5-step300
Updated
jh-parking/toolrl-grpo-1e-5-step300
Updated
jh-parking/toolrl-grpo-5e-6-step300
Updated
jh-parking/toolrl-grpo-3e-6-step300
Updated
jh-parking/Qwen3-8B-on-policy-distill-reverse-kld-llava-instruction
Image-Text-to-Text • 9B • Updated • 4
jh-parking/Qwen3-8B-SafeGRPO-Unsafe-Only
Image-Text-to-Text • 9B • Updated • 2
datasets 0
None public yet